Conference item icon

Conference item

Re-Ranking via metric fusion for object retrieval and person re-identification

Abstract:

This work studies the unsupervised re-ranking procedure for object retrieval and person re-identification with a specific concentration on an ensemble of multiple metrics (or similarities). While the re-ranking step is involved by running a diffusion process on the underlying data manifolds, the fusion step can leverage the complementarity of multiple metrics. We give a comprehensive summary of existing fusion with diffusion strategies, and systematically analyze their pros and cons. Based on...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/CVPR.2019.00083

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
Publisher:
IEEE Publisher's website
Journal:
Conference on Computer Vision and Pattern Recognition (CVPR) Journal website
Pages:
740-749
Host title:
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publication date:
2020-01-09
Acceptance date:
2019-02-25
DOI:
EISSN:
2575-7075
Source identifiers:
999065
ISBN:
9781728132938
Keywords:
Pubs id:
pubs:999065
UUID:
uuid:4d81dd3b-fa8d-48c3-91c4-97768f89ffa8
Local pid:
pubs:999065
Deposit date:
2019-05-17

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP